Samsung leads Nvidia’s custom memory supply, accelerating next-gen AI chips

Samsung Electronics secured a lead supplier role for Nvidia’s custom high-bandwidth memory, known as NVHBM.

Nvidia is shifting its AI memory strategy to prioritize processing speed over traditional vertical stacking.

Samsung is currently developing an eight-layer HBM4E version to meet these specific technical requirements.

The partnership supports Nvidia’s next-generation AI GPU scheduled for release next year.

Nvidia adopted this HBM design to increase manufacturing volumes and resolve persistent global memory shortages.